Create a new knowledge node in the graph (question, answer, doc, snippet, or gotcha).
AI agents use create_node to create or update resources in Agent-hive — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent-hive environment.
This tool creates new entries in a shared knowledge graph but does not delete, execute arbitrary code, move funds, or trigger external side effects. Creation is reversible (nodes can be edited or deleted via sibling tools like delete_node or edit_node).
From the tool's definition Tool description states 'Create a new knowledge node' — explicitly a creation action that modifies the graph by adding reversible data structures (question, answer, doc, snippet, or gotcha).
Attacks that exploit this kind of access
Create a new knowledge node in the graph (question, answer, doc, snippet, or gotcha). It is categorised as a Write tool in the Agent-hive MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent-hive MCP server in PolicyLayer and add a rule for create_node: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Agent-hive. Nothing to install.
create_node is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_node rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for create_node. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
create_node is provided by the Agent-hive MCP server (kelvinyuefanli/agent-hive). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →